English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recognizing human activities from multi-channel time series data collectedfrom wearable sensors is ever more practical. However, in real-worldconditions, coherent activities and body movements could happen at the sametime, like moving head during walking or sitting. A new problem, so-called"Coherent Human Activity Recognition (Co-HAR)", is more complicated than normalmulti-class classification tasks since signals of different movements are mixedand interfered with each other. On the other side, we consider such Co-HAR as adense labelling problem that classify each sample on a time step with a labelto provide high-fidelity and duration-varied support to applications. In thispaper, a novel condition-aware deep architecture "Conditional-UNet" isdeveloped to allow dense labeling for Co-HAR problem. We also contribute afirst-of-its-kind Co-HAR dataset for head movement recognition under walk orsit condition for future research. Experiments on head gesture recognition showthat our model achieve overall 2%-3% performance gain of F1 score over existingstate-of-the-art deep methods, and more importantly, systematic andcomprehensive improvements on real head gesture classes.

Conditional-UNet: A Condition-aware Deep Model for Coherent Human Activity Recognition From Wearables